The accuracy of phase demodulation has significant impact on the accuracy of fringe projection 3D measurement. Currently, researches based on deep learning methods for extracting wrapped phase mostly use U-Net as the subject of network. The connection method between its hierarchies has certain shortcomings in global information transmission, which hinders the improvement of wrapped phase prediction accuracy. We propose a single-shot phase demodulation method for fringe projection based on a novel full-scale connection network SE-FSCNet. The encoder and decoder of the SE-FSCNet have the same number of hierarchies but are not completely symmetrical. At the decoder a full-scale connection method and feature fusion module are designed so that SE-FSCNet has better abilities of feature transmission and utilization compared with U-Net. A channel attention module based on squeeze and excitation is also introduced to assign appropriate weights to features with different scales, which has been proved by the ablation study. The experiments conducted on the test set have demonstrated that the SE-FSCNet can achieve higher precision than the traditional Fourier transform method and the U-Net in phase demodulation.

The rotational speed vectors of the bearing balls affect their service life and running performance. Observing the actual rotational speed of the ball is a prerequisite for revealing its true motion law and conducting sliding behavior simulation analysis. To address the need for accuracy and real-time measurement of spin angular velocity, which is also under high-frequency and high-speed ball motion conditions, a new measurement method of ball rotation vectors based on a binocular vision system is proposed. Firstly, marker points are laid on the balls, and their three-dimensional (3D) coordinates in the camera coordinate system are calculated in real time using the triangulation principle. Secondly, based on the 3D coordinates before and after the movement of the marker point and the trajectory of the ball, the mathematical model of the spin motion of the ball was established. Finally, based on the ball spin motion model, the three-dimensional vision measurement technology was first applied to the measurement of the bearing ball rotation vector through formula derivation, achieving the analysis of bearing ball rolling and sliding characteristics. Experimental results demonstrate that the visual measurement system with the frame rate of 100 FPS (frames per second) yields a measurement error within ±0.2% over a speed range from 5 to 50 RPM (revolutions per minute), and the maximum measurement errors of spin angular velocity and linear velocity are 0.25 °/s and 0.028 mm/s, respectively. The experimental results show that this method has good accuracy and stability in measuring the rotation vector of the ball, providing a reference for bearing balls’ rotational speed monitoring and the analysis of the sliding behavior of bearing balls.

Binocular structured light systems are widely used in 3D measurements. In the condition of complex and local highly reflective scenes, to obtain more 3D information, binocular systems are usually divided into two pairs of devices, each having a Single Camera and a Projector (SCP). In this case, the binocular system can be seen as Dual Cameras-Projector (DCP) system. In the DCP calibration, the Left-SCP and Right-SCP need to be calibrated separately, which leads to inconsistent parameters for the same projector, thus reducing the measurement accuracy. To solve this problem and improve manoeuvrability, a coupled calibration method using an orthogonal phase target is proposed. The 3D coordinates on a phase target are uniquely determined by the binocular camera in DCP, rather than being calculated separately in each SCP. This ensures the consistency of the projector parameters. The coordinates of the projector image plane are calculated through the unwrapped phase, while the parameters are calibrated by the plane calibration method. In order to extract sub-pixel accuracy feature points, a method based on polynomial fitting using an orthogonal phase target is exploited. The experimental results show that the reprojection error of our method is less than 0.033 pixels, which improves the calibration accuracy.

Accurate camera calibration is crucial for achieving high-precision 3D measurements, particularly when using low-cost devices in long-range or complex depth environments where modeling distortion becomes significantly more challenging. Traditional calibration approaches often fail to capture focal-depth-dependent distortion due to their limited parametric structures, compromising reliability in demanding scenarios. To tackle these issues, we propose a two-step calibration process that combines geometric distortion modeling with learning-based refinement. In the first stage, we develop a Phased Distortion Attenuation Optimization (PDAO) algorithm, which gradually reduces distortion effects across varying depths. In the second stage, we introduce a neural network-based error compensation module (NN Model). It learns residual distortion patterns by taking image coordinates as input and producing undistorted coordinates based on the optimized intrinsic parameters. Experimental results demonstrate that our method significantly improves reprojection accuracy and robustness under wide-baseline and multiview settings. The proposed approach makes it particularly suitable for high-precision 3D vision applications in challenging or unconstrained environments.

The rapid advancement of 3D scanning technology now enables the capture of high-resolution point clouds, establishing a new data foundation for CAD model reconstruction in reverse engineering. However, existing point cloud segmentation algorithms confront three fundamental challenges: limited instance category generalization, inadequate noise resistance, and strong scenario dependency of parameters, which significantly restrict their effectiveness in industrial-grade applications. To address these issues, we propose a robust ridge-patterned instance segmentation algorithm specifically tailored for high-resolution point clouds of mechanical components with precision geometric features. Our unsupervised method consists of four main steps: The curvature coefficient calculation using a Determinantal Sampling (DetS) estimator and ridge points extraction via triangular threshold, the enhancement of ridge points, the adaptive-radius region growing method for surface segmentation, and the ridge points assignment via local plane fitting. Extensive experiments on synthetic (ABC-10) and real-world (OmniObject3D-8) demonstrate superior performance. Our method achieves an average mIoU of 95.52% on ABC-10 dataset, outperforming traditional methods and deep learning approaches. Notably, under 10% noise conditions, it maintains a robust mIoU of 87.11%, showcasing strong noise resilience. The algorithm’s parameter stability and resolution independence make it suitable for integration with the structured-light sensors in real-world measurement systems.

Point cloud completion is a fundamental yet challenging task in 3D computer vision. While existing two-stage methods have made significant progress in shape completion, they often overlook the critical issue of point density imbalance, leading to geometrically unsound results with illusory completeness. In this paper, we propose BD-TNet, a novel balanced density-aware point cloud completion method that systematically addresses this overlooked problem. Specifically, we design a Partial-Connected U-Net structure that strategically reduces top-layer skip connections to rebalance the influence between explicit features of partial inputs and abstract features for predicting missing regions, thereby generating uniformly distributed seed points. Furthermore, we introduce EmbeddingTrie, a Trie-like hierarchical shape prior dictionary that enables adaptive multi-scale prior fusion through a divide-and-conquer strategy. To directly constrain local point density, we devise an Elastic Potential Energy Loss that models point clouds as spring systems, effectively guiding the optimization toward balanced distributions. We evaluate our method on PCN, ShapeNet-34/55, and KITTI datasets, and the results demonstrate that BD-TNet achieves state-of-the-art performance on Density-aware Chamfer Distance while producing visually superior, complete point clouds with balanced density distribution.